IoT Botnet Detection and Classification using Machine Learning Algorithms for Improved Cybersecurity

Abstract

n this era of advanced technology, the interconnection of various devices has become a crucial aspect. As a solution to optimize this interconnectivity, the Internet of Things has emerged as a prominent solution. However, ensuring the security of Internet of Things systems is equally essential. Timely detection of potential attacks on Internet of Things systems can effectively mitigaterisks and minimize damages. In the present research, we investigated the efficacyof four algorithms, namely Decision Tree, K Nearest Neighbors , Random Forest, and Extreme Gradient Boosting , in detecting and classifying Internet of Thingsbotnets. Our findings demonstrate that all four algorithms exhibit remarkable effectiveness in detecting and classifying botnets. Among these algorithms, the Extreme Gradient Boosting algorithm achieved the highest accuracy, while the Decision Tree algorithm exhibited the shortest execution time. This study highlightsthe potential of machine learning algorithms in detecting and reducing securitythreats in Internet of Things devices. By leveraging these algorithms, it is possible to detect and classify botnets promptly, thus minimizing the risk of securitybreaches in Internet of Things systems.